Pub Date : 2022-01-31DOI: 10.1080/17686733.2022.2033531
Changmin Kim, Gwanyong Park, Hyangin Jang, Eui-Jong Kim
ABSTRACT The first step in establishing a retrofit strategy for an existing building is to identify the type of thermal defects in the building envelope. Infrared thermography is mainly used to detect thermal defects. However, the diagnosis results are subjectively influenced by the auditor’s experience. This study proposes a method for classifying thermal defects into material-related thermal bridges, geometrical thermal bridges, air leakages, and other thermal defects via thermal and visible images. To verify the performance of the proposed method, a field experiment was performed on a building in which thermal defects occurred. The results of the field experiment showed that the F-scores of the proposed method were 0.9707 for air leakage, 0.9000 for a material-related thermal bridge, 0.9775 for a geometrical thermal bridge, and 0.9228 for other defects. The results of this study show the potential for automatically classifying various types of defects that occur in building envelopes.
{"title":"Automated classification of thermal defects in the building envelope using thermal and visible images","authors":"Changmin Kim, Gwanyong Park, Hyangin Jang, Eui-Jong Kim","doi":"10.1080/17686733.2022.2033531","DOIUrl":"https://doi.org/10.1080/17686733.2022.2033531","url":null,"abstract":"ABSTRACT The first step in establishing a retrofit strategy for an existing building is to identify the type of thermal defects in the building envelope. Infrared thermography is mainly used to detect thermal defects. However, the diagnosis results are subjectively influenced by the auditor’s experience. This study proposes a method for classifying thermal defects into material-related thermal bridges, geometrical thermal bridges, air leakages, and other thermal defects via thermal and visible images. To verify the performance of the proposed method, a field experiment was performed on a building in which thermal defects occurred. The results of the field experiment showed that the F-scores of the proposed method were 0.9707 for air leakage, 0.9000 for a material-related thermal bridge, 0.9775 for a geometrical thermal bridge, and 0.9228 for other defects. The results of this study show the potential for automatically classifying various types of defects that occur in building envelopes.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"20 1","pages":"106 - 122"},"PeriodicalIF":2.5,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49433779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-06DOI: 10.1080/17686733.2021.2025019
C. Filippini, D. Cardone, D. Perpetuini, A. Chiarelli, L. Petitto, A. Merla
ABSTRACT Since birth, infants have been immersed in a social environment, often surrounded by artificial-intelligent-agents (AIAs). However, there is a paucity of work on infants’ psychophysiological responses, and their related interest, when interacting with AIAs. Here, the infants’ psychophysiological responses during interactions with an embodied robot and a virtual human/avatar presented on a screen are investigated. The experimental paradigm consists of a robot producing socially communicative gestures to babies as compared to a virtual human producing socially communicative gestures and linguistic interactions, such as linguistic nursery rhymes in American Sign Language. Psychophysiological responses were measured using thermal infrared imaging technology that tracks changes in cutaneous temperature, enabling contactless investigation of human autonomic functions. Crucially, it permits first-time inferences about changes in infants’ psychological, attentional, and emotional engagement in relation to agents and events in the world around them. Thermal signals analysis revealed a statistically significant difference in the infants’ physiological response to robot and avatar interactions indicating important differences in each agent’s ability to engage infants. Understanding infants’ psychophysiological responses to AIAs during the first year of life, which is a crucial period for human learning, lays bare how AIAs may impact infants’ emotional, social, and language learning and higher cognitive growth.
{"title":"Assessment of autonomic response in 6–12-month-old babies during the interaction with robot and avatar by means of thermal infrared imaging","authors":"C. Filippini, D. Cardone, D. Perpetuini, A. Chiarelli, L. Petitto, A. Merla","doi":"10.1080/17686733.2021.2025019","DOIUrl":"https://doi.org/10.1080/17686733.2021.2025019","url":null,"abstract":"ABSTRACT Since birth, infants have been immersed in a social environment, often surrounded by artificial-intelligent-agents (AIAs). However, there is a paucity of work on infants’ psychophysiological responses, and their related interest, when interacting with AIAs. Here, the infants’ psychophysiological responses during interactions with an embodied robot and a virtual human/avatar presented on a screen are investigated. The experimental paradigm consists of a robot producing socially communicative gestures to babies as compared to a virtual human producing socially communicative gestures and linguistic interactions, such as linguistic nursery rhymes in American Sign Language. Psychophysiological responses were measured using thermal infrared imaging technology that tracks changes in cutaneous temperature, enabling contactless investigation of human autonomic functions. Crucially, it permits first-time inferences about changes in infants’ psychological, attentional, and emotional engagement in relation to agents and events in the world around them. Thermal signals analysis revealed a statistically significant difference in the infants’ physiological response to robot and avatar interactions indicating important differences in each agent’s ability to engage infants. Understanding infants’ psychophysiological responses to AIAs during the first year of life, which is a crucial period for human learning, lays bare how AIAs may impact infants’ emotional, social, and language learning and higher cognitive growth.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"329 6","pages":"78 - 91"},"PeriodicalIF":2.5,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41286702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-05DOI: 10.1080/17686733.2021.2025018
Nabil Karim Chebbah, M. Ouslim, S. Benabid
ABSTRACT Mammography is widely used for identifying breast cancer. However, this technique is invasive, which causes X-ray tissue damage and very often fails to detect a certain tumour size. Thermography is another alternative, being non-ionising, non-invasive and able to detect abnormal breast conditions at an early stage. In this paper, we propose a new computer-aided diagnosis system based on artificial intelligence and thermography to help radiologists correctly diagnose breast diseases. One hundred and seventy infrared breast images are collected from an open-source database to feed a deep learning algorithm for automatic segmentation of breast thermograms. An intersection over a union of 89.03% is practically obtained using the U-net model. Textural evaluation and vascular network analysis are performed on the segmented thermograms to extract relevant features. Classifiers based on supervised learning algorithms are implemented using the extracted features to distinguish normal from abnormal thermograms. . We achieved an accuracy of 94.4%, a precision of 96.2%, a recall of 86.7%, an F1-score of 91.2% and a true negative rate of 98.3% when the developed approach was applied on a support vector machine. These two obtained results concerning both segmentation and classification are considered very motivating and encouraging compared to up-to-date methods.
{"title":"New computer aided diagnostic system using deep neural network and SVM to detect breast cancer in thermography","authors":"Nabil Karim Chebbah, M. Ouslim, S. Benabid","doi":"10.1080/17686733.2021.2025018","DOIUrl":"https://doi.org/10.1080/17686733.2021.2025018","url":null,"abstract":"ABSTRACT Mammography is widely used for identifying breast cancer. However, this technique is invasive, which causes X-ray tissue damage and very often fails to detect a certain tumour size. Thermography is another alternative, being non-ionising, non-invasive and able to detect abnormal breast conditions at an early stage. In this paper, we propose a new computer-aided diagnosis system based on artificial intelligence and thermography to help radiologists correctly diagnose breast diseases. One hundred and seventy infrared breast images are collected from an open-source database to feed a deep learning algorithm for automatic segmentation of breast thermograms. An intersection over a union of 89.03% is practically obtained using the U-net model. Textural evaluation and vascular network analysis are performed on the segmented thermograms to extract relevant features. Classifiers based on supervised learning algorithms are implemented using the extracted features to distinguish normal from abnormal thermograms. . We achieved an accuracy of 94.4%, a precision of 96.2%, a recall of 86.7%, an F1-score of 91.2% and a true negative rate of 98.3% when the developed approach was applied on a support vector machine. These two obtained results concerning both segmentation and classification are considered very motivating and encouraging compared to up-to-date methods.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"20 1","pages":"62 - 77"},"PeriodicalIF":2.5,"publicationDate":"2022-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47994331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-28DOI: 10.1080/17686733.2021.2019658
Kaixin Liu, Kai-Lun Huang, S. Sfarra, Jian-Hua Yang, Yi Liu, Yuan Yao
ABSTRACT Active infrared thermography is an important non-destructive testing method used for revealing defect structures in materials. In many applications, thermographic data processing is necessary to extract defect features from a large number of thermal images. This work proposes to use a factor analysis thermography (FAT) method that automatically extracts defect features from thermograms via exploratory factor analysis, in tandem with a fuzzy c-means (FCM) clustering algorithm to segment the defects and background. By means of factor rotation, factor analysis minimises the complexity of factor loadings and makes the results more interpretable. Consequently, the defect information is extracted while large signal-to-noise ratios are obtained. Employing the FCM image segmentation algorithm on factor loading images reduces the interference of background on human visual detection. Additionally, the parameter selection is emphasised and addressed. Experiments on a panel painting illustrate that the proposed method promotes the accuracy and efficiency of thermographic detection of defects, compared with the popular principal component thermography (PCT) method.
{"title":"Factor analysis thermography for defect detection of panel paintings","authors":"Kaixin Liu, Kai-Lun Huang, S. Sfarra, Jian-Hua Yang, Yi Liu, Yuan Yao","doi":"10.1080/17686733.2021.2019658","DOIUrl":"https://doi.org/10.1080/17686733.2021.2019658","url":null,"abstract":"ABSTRACT Active infrared thermography is an important non-destructive testing method used for revealing defect structures in materials. In many applications, thermographic data processing is necessary to extract defect features from a large number of thermal images. This work proposes to use a factor analysis thermography (FAT) method that automatically extracts defect features from thermograms via exploratory factor analysis, in tandem with a fuzzy c-means (FCM) clustering algorithm to segment the defects and background. By means of factor rotation, factor analysis minimises the complexity of factor loadings and makes the results more interpretable. Consequently, the defect information is extracted while large signal-to-noise ratios are obtained. Employing the FCM image segmentation algorithm on factor loading images reduces the interference of background on human visual detection. Additionally, the parameter selection is emphasised and addressed. Experiments on a panel painting illustrate that the proposed method promotes the accuracy and efficiency of thermographic detection of defects, compared with the popular principal component thermography (PCT) method.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"20 1","pages":"25 - 37"},"PeriodicalIF":2.5,"publicationDate":"2021-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44113753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-28DOI: 10.1080/17686733.2021.2010379
Saim Ervural, M. Ceylan
ABSTRACT Monitoring the body temperatures and evaluating the thermal asymmetry of newborns give an idea about neonatal diseases. Infrared thermography is a non-invasive, non-harmful, and non-contact modality that allows the monitoring of the body temperature distribution. Early diagnosis using a limited data set is extremely vital due to the high mortality rate in newborns and some difficulties in neonatal imaging. Thermography stands out as a useful tool in detecting neonatal diseases compared to other techniques. However, creating a thermogram database consisting of thousands of images from each class required by traditional artificial intelligence methods, is impossible due to the sensitivity of newborns. One of the meta-learning models that has recently gained success in applying limited data learning, especially one-shot, in various fields is Siamese neural networks. In this work, we perform a multi-class classification to provide pre-diagnosis to experts in disease detection using Siamese neural networks. By using two different optimisation techniques and data augmentation, critical diseases with only a few sample data are classified using the method tested in two- and three-class evaluation approaches. The results based on the disease type achieve 99.4% accuracy in infection diseases and 96.4% oesophageal atresia, 97.4% in intestinal atresia, and 94.02% in necrotising enterocolitis.
{"title":"Thermogram classification using deep siamese network for neonatal disease detection with limited data","authors":"Saim Ervural, M. Ceylan","doi":"10.1080/17686733.2021.2010379","DOIUrl":"https://doi.org/10.1080/17686733.2021.2010379","url":null,"abstract":"ABSTRACT Monitoring the body temperatures and evaluating the thermal asymmetry of newborns give an idea about neonatal diseases. Infrared thermography is a non-invasive, non-harmful, and non-contact modality that allows the monitoring of the body temperature distribution. Early diagnosis using a limited data set is extremely vital due to the high mortality rate in newborns and some difficulties in neonatal imaging. Thermography stands out as a useful tool in detecting neonatal diseases compared to other techniques. However, creating a thermogram database consisting of thousands of images from each class required by traditional artificial intelligence methods, is impossible due to the sensitivity of newborns. One of the meta-learning models that has recently gained success in applying limited data learning, especially one-shot, in various fields is Siamese neural networks. In this work, we perform a multi-class classification to provide pre-diagnosis to experts in disease detection using Siamese neural networks. By using two different optimisation techniques and data augmentation, critical diseases with only a few sample data are classified using the method tested in two- and three-class evaluation approaches. The results based on the disease type achieve 99.4% accuracy in infection diseases and 96.4% oesophageal atresia, 97.4% in intestinal atresia, and 94.02% in necrotising enterocolitis.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"19 1","pages":"312 - 330"},"PeriodicalIF":2.5,"publicationDate":"2021-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48435830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-13DOI: 10.1080/17686733.2021.2010380
Duo Yixian, Hou Dexin, Dong Zewen, Ye Shuliang
ABSTRACT This work proposed a non-destructive evaluation method using IR camera for prismatic Li-ion cell to evaluate the thermal conductivity and the thermal contact resistance (TCR) for both in-plane and cross-plane directions. In this study, experiments were conducted using two 50-Ah cells and two 75-Ah cells. The cross-plane parameters exhibit significant repeatability, as evidenced in three independent tests. However, the in-plane parameters could only be inferred within the best possible range of values. The cross-plane TCRs are negligible, whereas the in-plane TCRs are greater than 0.012 KW−1m2 and 0.016 KW−1m2 for the two individual cells.
{"title":"Non-destructive Evaluation Method for Thermal Parameters of Prismatic Li-ion Cell Using Infrared Thermography","authors":"Duo Yixian, Hou Dexin, Dong Zewen, Ye Shuliang","doi":"10.1080/17686733.2021.2010380","DOIUrl":"https://doi.org/10.1080/17686733.2021.2010380","url":null,"abstract":"ABSTRACT This work proposed a non-destructive evaluation method using IR camera for prismatic Li-ion cell to evaluate the thermal conductivity and the thermal contact resistance (TCR) for both in-plane and cross-plane directions. In this study, experiments were conducted using two 50-Ah cells and two 75-Ah cells. The cross-plane parameters exhibit significant repeatability, as evidenced in three independent tests. However, the in-plane parameters could only be inferred within the best possible range of values. The cross-plane TCRs are negligible, whereas the in-plane TCRs are greater than 0.012 KW−1m2 and 0.016 KW−1m2 for the two individual cells.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"20 1","pages":"14 - 24"},"PeriodicalIF":2.5,"publicationDate":"2021-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43652155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-29DOI: 10.1080/17686733.2021.1989181
N. Vinnichenko, A. Pushtaev, Y. Plaksina, A. Uvarov
ABSTRACT New experimental technique, based on IR thermography, is proposed to measure the surface pressure for dilute monomolecular films of surfactants on a liquid surface. The surfactant molecules are distributed unevenly along the surface, which leads to the formation of surface regions of two kinds. Part of the surface is covered with surfactant film, which suppresses the surface renewal and inhibits the heat transfer between the surface and the bulk liquid. Thus, these regions possess lower temperature compared to the rest of the surface, free of surfactant and exhibiting both buoyant and thermocapillary convection. High sensitivity of the modern IR cameras allows the measurement of the temperature difference between the surface regions, from which the surface pressure can be derived. Experiments with myristic acid are performed for different values of the surface temperature and mean concentration of the surfactant. The results demonstrate that it is possible to measure the surface pressure for liquid-expanded films with area per molecule up to . The derived parameters of 2D van der Waals gas are in agreement with published data . The proposed technique can also be used to compare the contamination level in dilute films of insoluble and soluble surfactants.
{"title":"Infrared thermography applied to the surface pressure measurements in insoluble surfactant monolayers","authors":"N. Vinnichenko, A. Pushtaev, Y. Plaksina, A. Uvarov","doi":"10.1080/17686733.2021.1989181","DOIUrl":"https://doi.org/10.1080/17686733.2021.1989181","url":null,"abstract":"ABSTRACT New experimental technique, based on IR thermography, is proposed to measure the surface pressure for dilute monomolecular films of surfactants on a liquid surface. The surfactant molecules are distributed unevenly along the surface, which leads to the formation of surface regions of two kinds. Part of the surface is covered with surfactant film, which suppresses the surface renewal and inhibits the heat transfer between the surface and the bulk liquid. Thus, these regions possess lower temperature compared to the rest of the surface, free of surfactant and exhibiting both buoyant and thermocapillary convection. High sensitivity of the modern IR cameras allows the measurement of the temperature difference between the surface regions, from which the surface pressure can be derived. Experiments with myristic acid are performed for different values of the surface temperature and mean concentration of the surfactant. The results demonstrate that it is possible to measure the surface pressure for liquid-expanded films with area per molecule up to . The derived parameters of 2D van der Waals gas are in agreement with published data . The proposed technique can also be used to compare the contamination level in dilute films of insoluble and soluble surfactants.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"20 1","pages":"1 - 13"},"PeriodicalIF":2.5,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46621289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1080/17686733.2021.1991746
S. Schramm, P. Osterhold, R. Schmoll, A. Kroll
ABSTRACT In recent years, due to the availability of affordable 3D sensors and the increased computing power, various methods for the generation of 3D thermograms have been developed. 3D thermal imaging describes the fusion of geometry and temperature data. A well-established approach is the fusion of data from depth and long-wave infrared (LWIR) cameras. However, these models generated in real-time have the limitation that the model size is limited due to inefficient data storage approach. Newer algorithms from Computer Vision promise to overcome this limitation by more efficient data handling and storage. Within this work, three state of the art 3D reconstruction algorithms from the computer vision community are compared and one of these is extended by overlaying thermal data, which allows the creation of large-scale 3D thermograms with a portable 3D measurement system. For this purpose, a geometric calibration is required, the data structure is adapted, and the handling of cyclic non-uniformity corrections required for uncooled LWIR cameras is described. The results will show exemplary 3D thermograms and the advantages compared to current existing systems.
{"title":"Combining modern 3D reconstruction and thermal imaging: generation of large-scale 3D thermograms in real-time","authors":"S. Schramm, P. Osterhold, R. Schmoll, A. Kroll","doi":"10.1080/17686733.2021.1991746","DOIUrl":"https://doi.org/10.1080/17686733.2021.1991746","url":null,"abstract":"ABSTRACT In recent years, due to the availability of affordable 3D sensors and the increased computing power, various methods for the generation of 3D thermograms have been developed. 3D thermal imaging describes the fusion of geometry and temperature data. A well-established approach is the fusion of data from depth and long-wave infrared (LWIR) cameras. However, these models generated in real-time have the limitation that the model size is limited due to inefficient data storage approach. Newer algorithms from Computer Vision promise to overcome this limitation by more efficient data handling and storage. Within this work, three state of the art 3D reconstruction algorithms from the computer vision community are compared and one of these is extended by overlaying thermal data, which allows the creation of large-scale 3D thermograms with a portable 3D measurement system. For this purpose, a geometric calibration is required, the data structure is adapted, and the handling of cyclic non-uniformity corrections required for uncooled LWIR cameras is described. The results will show exemplary 3D thermograms and the advantages compared to current existing systems.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"19 1","pages":"295 - 311"},"PeriodicalIF":2.5,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41910561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-07DOI: 10.1080/17686733.2021.1974209
Aayesha Hakim, R. Awale
ABSTRACT A major concern for women’s health in today’s age is breast cancer. Thermography is an upcoming technology that is painless, private and relatively cheap to screen breast health. The presence of asymmetric hot blood vessel patterns in the breast thermogram portrays an abnormality. Proper extraction of these hotspots from the breast can help build a reliable breast cancer detection system and play a critical role in knowing the extent of spread of the cancer. In this work, segmentation of mammary thermograms is performed to extract the hottest blood vessel patterns using five state-of-the-art image segmentation methods. The proposed work is tested on the benchmark breast thermogram public dataset available at the Visual Lab. The most vascularised areas of each breast are extracted, and their areas are matched with the patches in the ground truth images. Based on metrics like DICE similarity coefficient and Jaccard index, it is concluded that particle swarm optimisation (PSO) algorithm and multi-seed region-growing technique provide the best segmentation results that are closer to the ground truth images. This indicates that infrared imaging is a promising tool that can act as a catalyst in predicting breast anomalies.
{"title":"Extraction of hottest blood vessels from breast thermograms using state-of-the-art image segmentation methods","authors":"Aayesha Hakim, R. Awale","doi":"10.1080/17686733.2021.1974209","DOIUrl":"https://doi.org/10.1080/17686733.2021.1974209","url":null,"abstract":"ABSTRACT A major concern for women’s health in today’s age is breast cancer. Thermography is an upcoming technology that is painless, private and relatively cheap to screen breast health. The presence of asymmetric hot blood vessel patterns in the breast thermogram portrays an abnormality. Proper extraction of these hotspots from the breast can help build a reliable breast cancer detection system and play a critical role in knowing the extent of spread of the cancer. In this work, segmentation of mammary thermograms is performed to extract the hottest blood vessel patterns using five state-of-the-art image segmentation methods. The proposed work is tested on the benchmark breast thermogram public dataset available at the Visual Lab. The most vascularised areas of each breast are extracted, and their areas are matched with the patches in the ground truth images. Based on metrics like DICE similarity coefficient and Jaccard index, it is concluded that particle swarm optimisation (PSO) algorithm and multi-seed region-growing technique provide the best segmentation results that are closer to the ground truth images. This indicates that infrared imaging is a promising tool that can act as a catalyst in predicting breast anomalies.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"19 1","pages":"347 - 365"},"PeriodicalIF":2.5,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49168889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-11DOI: 10.1080/17686733.2021.1962096
R. Olbrycht
ABSTRACT The work proposes a novel method for sensitivity modelling of uncooled thermal cameras for optical gas imaging purposes. Such cameras use warm interference filters for better gas leak contrast at the cost of decreased sensitivity. With the presented method, it is possible to estimate this sensitivity without the need for physically installing a filter inside the camera. It can be done for any chosen background temperature and an arbitrary filter with known spectral transmission characteristic, which is often found in the filter manufacturer’s documentation. The proposed method requires prior measurement of the camera calibration curve before filter installation. In addition, this method may be used for estimating, how camera noise equivalent temperature difference will change after filter installation. With the aid of new parameter gas equivalent blackbody digital level difference, one may also verify, whether in particular measurement scenario gas leak will be visible or not. The performance of the proposed method is validated with five different filters and broadband uncooled thermal imaging camera.
{"title":"A novel method for sensitivity modelling of optical gas imaging thermal cameras with warm filters","authors":"R. Olbrycht","doi":"10.1080/17686733.2021.1962096","DOIUrl":"https://doi.org/10.1080/17686733.2021.1962096","url":null,"abstract":"ABSTRACT The work proposes a novel method for sensitivity modelling of uncooled thermal cameras for optical gas imaging purposes. Such cameras use warm interference filters for better gas leak contrast at the cost of decreased sensitivity. With the presented method, it is possible to estimate this sensitivity without the need for physically installing a filter inside the camera. It can be done for any chosen background temperature and an arbitrary filter with known spectral transmission characteristic, which is often found in the filter manufacturer’s documentation. The proposed method requires prior measurement of the camera calibration curve before filter installation. In addition, this method may be used for estimating, how camera noise equivalent temperature difference will change after filter installation. With the aid of new parameter gas equivalent blackbody digital level difference, one may also verify, whether in particular measurement scenario gas leak will be visible or not. The performance of the proposed method is validated with five different filters and broadband uncooled thermal imaging camera.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"19 1","pages":"331 - 346"},"PeriodicalIF":2.5,"publicationDate":"2021-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46308311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：